A new complex system fault detection method based on belief rule base for unreliable interval values

Abstract

Equipment failures such as milling machines and inertial navigation systems can affect their normal operation, resulting in economic losses and personal injury in severe cases. Therefore, fault detection is of great importance. Belief rule base (BRB) is an expert system that plays an important role in fault detection. The traditional BRB has some problems in the explosion of the number of combination rules, the process of model inference, and the process of parameter optimization. To better deal with the above problems, this paper proposes a complex system fault detection method based on an interval-valued belief rule base (FDIR) and provides the construction and inference process of the method. In the method construction, the form of interval value and disjunction rules are introduced to solve the problem of the number explosion of combination rules, the indicator reliability is added to improve the accuracy of the method, and a new calculation method of rule availability is proposed. In the inference process, twice fusions are made based on evidence reasoning (ER) analysis algorithm and ER rule algorithm respectively to deal with the interval uncertainties. Moreover, the proposed FDIR method is optimized by the projection covariance matrix adaptive evolutionary strategy algorithm (P-CMA-ES). Finally, the effectiveness of the proposed method was verified through the research on milling fault detection and the experimental verification of inertial navigation system fault detection. The superiority of the model was also confirmed through comparative experiments.

An interpretable spacecraft flywheel system health status assessment method under perturbation

“…In contrast, models constructed on the basis of existing knowledge can have certain limitations in their processing ability when parsing complex nonlinear associations between input and output variables [20]. Since these models are usually simple in structure and clear in mathematical expression, it is difficult to reveal the deep and real connections between the variables, especially when the relationships are extremely complex and present nonlinear characteristics [21]. Moreover, it is challenging to obtain sufficient data samples in complex systems, which are characterized by high values and short life cycles [22].…”